Cody Menefee (Firecrawl) presents a talk on applying AI agents to pasture-based livestock farming. Drawing on his experience raising backyard turkeys in Nashville and exploring small-scale farming economics, he argues that rotational grazing — moving cattle daily across paddocks so grass can rest — improves outcomes for animals, consumers, and land but is limited by the labor of deciding when and where to move the herd. GPS virtual-fencing collars handle movement, but assessment of grass conditions still relies on human observation. He proposes putting a language model in the loop: combining data from trail cameras (drones face regulatory limits; satellites lack resolution), animal locations, and drought conditions to suggest the next paddock for a farmer to confirm. He identifies three remaining blockers — building a knowledge base from farmer YouTube channels and research papers (his Open Pasture project, using Firecrawl), computer vision for biomass and biodiversity, and closed proprietary collar ecosystems — and calls for an open collar platform. # Video Identity Observations ## Source Overview - **Title:** *You're Not Thinking Big Enough: Rebuilding Food Systems with AI Agents — Cody Menefee, Firecrawl* - **Format:** A conference talk transcript; the speaker self-identifies throughout. No curated metadata beyond the title was supplied. ## Explicit Self-Descriptions (Creator Claims) ### Speaker identity - Cody introduces himself as being **"on the growth team at Firecrawl"**, which he describes as building **"context for AI agents… a series of web data APIs to give your agents access to the web."** - He explicitly rejects formal engineering credentials: *"I have no credentials that qualify me for this talk"* and *"I actually don't really like taking the title of software engineer… I am the vibe coder most of you all are scared of. I use AI agents all day long. I don't have any syntax memorized."* - Personal background claimed: grew up in Kentucky, blue-collar work (bartender, mechanic, server), lives in Nashville, husband and father of two. ### Project and employer claims - **Firecrawl** — described as "building the context layer for AI"; the talk ends with an explicit recruiting pitch: *"Firecrawl is where we're building the context layer for AI, and I hope you can come build it with us… we're hiring."* - **Open Pasture** — described as his open source project, *"the actual repository I put this information in to make it available to any farmer."* ## Observable Presentation Patterns ### Intended audience - The talk addresses a **developer/AI-engineering conference audience**, evidenced by: - Framing of "building software for people who build software for people who build software." - References to **MCPs, SaaS, LLMs, deterministic algorithms, vibe coding**. - A direct **call to action** for attendees: *"I need someone to make me a collar… the APIs need to be open"* and an appeal to join Firecrawl. - The audience is assumed to be technically fluent but not agriculturally knowledgeable: *"I have a feeling most of you did not expect to learn about cows and grass and farming today."* ### Claimed scope - The talk claims a **thesis-level scope**: applying AI agents to "big, real-world physical problems" — specifically **autonomous pasture rotation / rotational grazing** for grass-fed livestock. - Three stated goals for the talk: 1. *"Convince you all to pursue bigger ideas."* 2. Discuss farming (a personal passion: *"if you corner me anywhere at any time, there's a good chance I will talk to you about farming"*). 3. Recruit for Firecrawl. - Domain scope extends to **livestock agriculture broadly**: rotational grazing, virtual fencing (Halter, No Fence), remote sensing options (drones, Planet satellites, trail cams), multi-species stacking (Pasturebird), and right-to-repair concerns. ### Demonstrated (not just claimed) presentation style - **Playful, self-deprecating tone:** jokes about a branded letterman jacket, hauling turkeys on a Tesla roof, and a "Eat Me" chicken packaging concept. - **Rivalry framing for attention:** *"Theo stole my talk… I submitted the name for this talk a month before Theo put his video out."* - **Concrete personal anecdotes as credibility substitutes:** raising 10 backyard turkeys in a residential Nashville neighborhood, nearly leaving engineering to farm. ## Evidence Notes - All audience and scope claims above are drawn from direct transcript quotations; no channel-level conclusions are drawn from a single talk. - The Firecrawl and Open Pasture descriptions are **creator claims**, not independently verified within this material. - No metadata beyond the title was provided; the title itself corroborates the speaker name (Cody Menefee), affiliation (Firecrawl), and thesis ("You're Not Thinking Big Enough"). # Delivery Observation: Cody Menefee — "You're Not Thinking Big Enough" ## Overall Delivery Style The speaker delivers a **conversational, humor-forward technical talk** that pairs self-deprecation with confident evangelism. The register is casual throughout, marked by filler words ("um," "uh"), but the pacing stays energetic and the structure is clearly signposted. ## Recurring Patterns ### 1. Self-Deprecating Openings and Credential Disclaimers A stable pattern: he repeatedly undercuts his own authority before asserting it. > "I actually have no credentials that qualify me for this talk, but nonetheless I'm going to do my best to give it." > "I'm pretty averse to that. Feels like stolen valor because I am the vibe coder most of you all are scared of." He pairs disclaimers with unconventional proof-of-credibility stories: > "a bit of credential I do have is this is a real picture of me hauling turkeys on top of my Tesla" ### 2. jokes Acknowledged as Jokes / "Playing the Bit" He explicitly frames his own humor and staging: > "I put this picture up here because this jacket so far has not actually landed as well as I thought it would. No one gets the joke." > "We intentionally tried to play into the bit a little bit." ### 3. Progressive Specificity as a Teaching Device He narrows scope step-by-step when introducing the topic: > "Today we're actually going to talk about farming. And yes, I actually mean farming. Uh more specifically, I mean livestock farming. And even more specifically, I mean automating pasture rotation for grass-fed livestock systems." ### 4. Direct Address and Audience Challenges He frequently speaks straight to the audience with second-person framing: > "I'm here to tell you you're not thinking big enough." > "I'm here so you're going to [learn about cows and grass]." > "if you corner me anywhere at any time, there's a good chance I will talk to you about farming" ### 5. Colloquial Intensifiers Recurring casual phrases used for emphasis: - **"a pain in the ass"** — used twice: "It is a pain in the ass to actually raise animals on grass" and "From an industry standpoint, I think it's really a pain in the ass." - **"take my word for it"** — deflecting depth: "You can find me later if you need me to tell you why it's better... Take my word for it. Let's start there." - **"I can give you a whole TED Talk on each of those"** — signaling offloaded depth, used similarly again later ("I can give you a whole bunch of channels you can go down rabbit holes on"). ### 6. Explicit Talk Structure Signposting He announces goals and takeaways numerically: > "three things I want to get accomplished in this talk is one, convince you all to pursue bigger ideas..." > "the three things I really hope you all take away from this talk is one..." He also uses numbered problem breakdowns: "There's three main blockers that I think need to exist." ## Teaching Habits - **Concrete numbers as anchors**: "97% of cows are still currently uh finished on feedlots. 3% are raised on pasture"; "move them every single day"; "1 by 1 m resolution." - **Anticipating and correcting audience assumptions**: "If you think about grass-fed uh beef, you might think of I have 100 cows, 100 acres... That's not quite how it works." - **Personal anecdotes as conceptual bridges**: the turkey-on-Tesla story and the "eat me" chicken packaging story both precede and motivate the pivot to scaling farming. - **Call to action as a closing device**: "I need someone to make me a collar"; "we're hiring"; "reach out to me." - **Naming real companies and projects**: Halter, No Fence, Planet, Pasturebird, John Deere, plus his own "Open Pasture" — grounding claims in identifiable references. ## Vocabulary and Register - Dominated by **plain-spoken, Blue-Collar-inflected language** ("good old guys out in Missouri, Tennessee, Kentucky," "farmers are pretty scrappy and like to heal their own things"). - Technical terms are introduced with in-line definitions: "ruminant is a type of animal, cows, sheep, goats... They uh digest it in the rumen... which is an organ that's what they're called ruminants." - Conversational hedges appear even on strong claims: "I don't think it's as good, or I think I can make it better, if I'm being totally honest with you." ## Isolated Moments (Lower Confidence) - The opening joke about the branded jacket failing to land is a single moment; whether self-aware humor is a routine opening device cannot be confirmed from one talk. - The playful rivalry framing ("Theo stole my talk") appears only once and may be event-specific rather than a stable pattern. - The phrase "drop an LLM in the middle of this loop" / "drop an LLM in the center" appears twice, suggesting a signature phrasing, but evidence is thin within a single video. ## Summary of Stable-Looking Patterns 1. Self-deprecation immediately followed by confident claims. 2. Progressive narrowing of topic scope when teaching. 3. Explicit numeric signposting of goals and takeaways. 4. Colloquial intensifiers ("pain in the ass," "take my word for it") alongside technical content. 5. Direct second-person audience challenge paired with a recruitment call to action. # Observation Record: "You're Not Thinking Big Enough: Rebuilding Food Systems with AI Agents" **Speaker:** Cody Menefee (identified via title metadata and self-introduction in transcript), Growth team at Firecrawl. --- ## Speaker's Stated Background & Credentials - Self-identifies as having **no formal credentials** qualifying him for the talk: *"the short version is I actually have no credentials that qualify me for this talk, but nonetheless I'm going to do my best."* - Grew up in Kentucky; blue-collar background (bartender, mechanic, server); **never actually a farmer**. - Describes himself as a **"vibe coder"**: no syntax memorized, not proficient in a coding language, uses AI agents daily; is *"pretty averse"* to the title of software engineer, calling it *"stolen valor."* - Anecdotes offered as experience: raised **10 turkeys** in a Nashville backyard (where turkeys are not permitted), hauled them on his Tesla roof to a processor; nearly left engineering to raise chickens but abandoned it because *"it's actually really hard to make any money farming"* and he has a wife and two kids. --- ## Core Position: Livestock Should Be on Pasture - **Claim:** Animals belong on grass — *"better for the animal, the consumer, the farmer, the ecosystem."* He explicitly declines to argue this in the talk: *"Take my word for it."* - **Qualification:** He states he is **not anti-containment farming** — *"I think there's a reason we needed to do that"* — but contends more animals could be on grass. - Cited figure: **97% of cows are finished on feedlots; 3% raised on pasture.** - **Bottleneck identified:** *"Labor is the bottleneck."* Proper pasture management requires moving animals constantly (rotational grazing across daily paddocks), moving fences, water, and record-keeping every day. ## Diagnosed Problem - Existing solutions: **virtual-fence collar companies** — Halter (Peter Thiel investment, $2B valuation, per the speaker) and No Fence. - **Residual gap:** collars let farmers move animals remotely, but *"you have to know where to move the animals."* He asserts this is **not a science**: grass growth varies with drought, rainfall, and paddock impact; today it's solved by farmers making *"intuitive decisions"* with *"eyeballs on the grass."* - Additional constraint: grass has a **juvenile "sweet spot"** — grazing too short or too tall reduces regrowth and palatability. ## Proposed Technical Approach - Drop an **LLM into the decision loop** for autonomous grazing operations, reasoning over multiple inputs: GPS animal locations, historical/planned movement, drought conditions, grass height across the farm — at herd, farm, and ecosystem levels of relation. - Data-gathering options he evaluates, with stated tradeoffs: - **Drone orthomosaic maps:** high fidelity, but requires farmer skill upgrades, line-of-sight regulation, and *"there currently isn't a jurisdiction in the world that has approved autonomous drones"* — a major bottleneck. - **Satellites (Planet, daily 1m resolution):** his *"most favorite option today,"* but resolution limits what can be determined from orbit. - **Trail cams with reference objects:** a friend's research setup at Missouri Lincoln University for measuring grass height relative to a fixed object. - Expected payoff: optimizing the whole system yields *"more animals on fewer acres,"* enabling pasture systems to compete with feedlots. ## Three Stated Blockers 1. **Knowledge base** — rotational-grazing knowledge is *"locked up in primarily YouTube videos"*; he is scraping YouTube and research papers (arXiv) using Firecrawl, published in his open-source project **Open Pasture**. 2. **Visualization layer** — needs to capture **biomass** and long-term **biodiversity** data (cool/warm-season grasses, legumes) so cattle get macronutrients/micronutrients from grass alone, ideally without hay or mineral supplementation. 3. **Open collars** — his strongest criticism in the talk: > *"While I appreciate the technology they're trying to push forward I have a pretty strong disagreement with them... they require you buy their collars, and you can't plug your own software into their collars."* - He acknowledges the business logic (*"From a business standpoint, I get why this is"*) but calls it *"a pain in the ass"* from an industry standpoint, and claims he believes he can build better software himself (*"if I'm being totally honest with you"*). - **Explicit call to action:** build an off-the-shelf collar with open patents and open APIs; he ties this to right-to-repair sentiment and farmer animosity toward John Deere. ## Extension: Stacking Species - Chickens (non-ruminants) can be stacked on rotations, citing **Pasturebird's** automated rolling chicken house as inspiration. - Claimed benefits: chicken droppings fertilize grass; running chickens behind ruminants reduces parasite load, lowering medication costs and producing stronger breeding stock over time. --- ## Broader Argument & Takeaways (as stated) - Conference culture critique: too much effort on *"building software for people who build software for people"* — *"another MCP for another SaaS solution at another company."* - His contention against the prevailing engineering view: > *"I hear a lot of engineers talk about how we turn LLMs into deterministic processes, and my contention is actually there's a lot of problems that you can't solve with deterministic algorithms."* - *"There isn't a next best paddock to move to. There's just your best guess."* The LLM should make suggestions a **human confirms or denies**. - Explicit self-interested motivations, stated openly: *"I'm just really trying to take advantage of a captive audience"* (to talk about farming) and recruiting — *"hopefully, I can convince you to come work at Firecrawl."* --- ## Notable Tensions & Qualifications (Preserved) - **Credential tension:** he argues for transforming livestock agriculture while repeatedly disclaiming farming and engineering expertise. - **Anti-determinism vs. optimization:** he frames the problem as one where LLMs make best guesses, yet also describes *"if you can optimize this entire picture"* — the talk holds both "best guess" and "optimization" framings without reconciling them. - **Collar companies:** appreciation for the technology paired with *"a pretty strong disagreement"* over closed business models, plus an unverified self-assessment (*"I don't think it's as good"*). - **Humor/non-serious framing:** the letterman jacket bit, the "Theo stole my talk" rivalry claim (his own submitted title predating Theo's video, per his account), and the turkey/Tesla anecdotes are presented as asides rather than evidence. # Video Attribution & Provenance Record ## Speaker Identification | Speaker | Role | Basis | |---|---|---| | **Cody Menefee** | Speaker; self-identified member of the **growth team at Firecrawl** | Self-introduction in transcript ("My name is Cody. I'm on the growth team at Firecracker [Firecrawl]") | | **Theo** | Third party, not present in video | Referenced only — speaker claims Theo published a video titled *"You Need to Think Bigger"* roughly a month before this talk | > Note: Speaker's affiliation stated as Firecrawl (title metadata confirms); transcript phonetically renders it "Firecracker"/"Fire Corral"/"Fire fall" in places. ### Speaker's stated background (self-reported) - Grew up in Kentucky; blue-collar work history (bartender, mechanic, server); no farming credentials. - Self-described "vibe coder" who uses AI agents daily without formal coding proficiency. - Lived in Nashville; raised 10 turkeys in his backyard (depicted on Tesla roof); nearly left engineering to farm chickens. --- ## Referenced Sources & Third Parties ### Companies / Organizations - **Firecrawl** — speaker's employer; builds web data APIs / "context layer for AI agents." - **Halter** — GPS collar company; speaker cites **Peter Thiel investment at a $2 billion valuation** (third-party claim, unverified in source). - **No Fence** — GPS virtual fencing collar company. - **Planet** — satellite imaging company; speaker claims daily global imagery at **1m × 1m resolution** (third-party claim). - **Pasturebird** — automated mobile chicken coop company; cited as catalyst for the speaker's interest. - **Missouri Lincoln University** — a friend of the speaker works there as a research grad assistant (trail-cam grass measurement photo). ### Projects & Claims of the Speaker - **Open Pasture** — speaker's open-source repository containing knowledge scraped from YouTube videos and research papers (archived papers) on pasture rotation. - Claim: **97% of cows are finished on feedlots; 3% raised on pasture** (speaker's figure, no source given in transcript). - Claim: **No jurisdiction has approved autonomous drones** for pasture monitoring applications (speaker's claim). --- ## Promotional Content — Flagged - **Recruitment promotion**: Explicit closing call to action to work at Firecrawl ("we're hiring… here's all the job postings"). - **Product promotion**: Firecrawl positioned as the tool used to build the described knowledge base; framing that Firecrawl solves the "context problem." - **Ideological positioning**: Speaker openly states a "strong disagreement" with Halter/No Fence's closed-collar model and pitches for an open-API alternative — promotional framing for his preferred ecosystem. --- ## Cited Evidence Channels — Availability - No cited sources are directly retrievable from the video: no URLs, papers, channel names, or job postings are legible in the transcript (slides referenced but not supplied). - The "friend's" trail-cam photo and turkey photos are described but not verifiable from text alone. - Comment availability: not indicated in the supplied material. --- ## Uncertainty Notes - Speaker acknowledges having "no credentials that qualify me for this talk" — all farming/agronomy claims are self-taught practitioner claims, not sourced citations. - The Theo priority dispute (who first used the "think bigger" framing) is one-sided, from the speaker only. - Figures (97%/3%, $2B valuation, 1m resolution) are stated without in-transcript citations. \>\> All right. Hello everybody. My name is Cody. Um I put this picture up here because this jacket so far has not actually landed as well as I thought it would. No one gets the joke. Um so this was to really put it in front of your face. I don't just enjoy wearing heavily branded letterman jacket. We intentionally tried to play into the bit a little bit. Um so, my name is Cody. I'm on the growth team at Firecracker. Um and today I'm here to tell you you're not thinking big enough. Um but before I actually get into that, I have to address a bit of an elephant in the room which is Theo stole my talk. Uh Theo put out a video about a month ago uh called uh you need to think bigger. But I would like to say I submitted the name for this talk a month before Theo put his video out. I didn't steal his talk. He stole my talk. So, um Today we're actually going to talk about farming. And yes, I actually mean farming. Uh more specifically, I mean livestock farming. And even more specifically, I mean automating pasture rotation for grass-fed livestock systems. Um I have a feeling most of you did not expect to learn about cows and grass and farming today, but I'm here so you're going to. Uh little bit of background on who I am and why maybe you should listen to me. Uh the short version is I actually have no credentials that qualify me for this talk, but nonetheless I'm going to do my best to give it. Uh I grew up in Kentucky. Uh have a background of blue collar work. I was a bartender, a mechanic, a uh um a server, uh a whole bunch of things. Uh never actually a farmer though. Um and then I sort of found my way into engineering, uh software development, etc. I actually don't really like taking the title of software engineer. Um I'm pretty averse to that. Feels like stolen valor because I am the vibe coder most of you all are scared of. I use AI agents all day long. I don't have any syntax memorized. I am not proficient in any particular coding language, but I will crank out some stuff on a weekend. But today I actually work at Firecrawl where we're building context for AI agents. We have a series of web data APIs to give your agents access to the web. Again, I said I'm on the growth team, but today we're actually getting into some more farming stuff. But first a bit of credential I do have is this is a real picture of me hauling turkeys on top of my Tesla and I do still have a crack in that glass ceiling because of it. This was in Nashville where I live in the middle of a residential neighborhood where you are not allowed to raise turkeys, but I raised 10 turkeys in my backyard cuz I wanted to know what it was like to actually raise livestock myself that I would eat. It's a very mentally difficult process to be mentally honest, but this was me loading them up onto the roof of my Tesla and then I drove for 3 hours with them to the processor. Had to stop at a supercharger on the way and lots of people were taking pictures and what I can tell you is if your range is sufficiently decreased when you have a giant windbreak full of turkeys on top of the roof. So that was quite the anxious drive I can tell you. I also almost left engineering to be a farmer. I really wanted to raise chickens. This is a real product image that I came up with. I wanted to wrap turkeys in white wrapping and literally just slapped the word eat me on top of it. I thought it was provocative. I thought it would get you to buy chickens, but I realized it's actually really hard to make any money farming. Surprise, surprise. And I have a wife. I have two kids. It didn't feel right to ask them to give up the lives they had so that I could go cosplay as a farmer and raise chickens. So I decided to pivot and see if there were ways that we could scale farming itself and the the types of systems that I'm interested in when it comes to livestock agriculture. So, three things I want to get accomplished in this talk is one, convince you all to pursue bigger ideas. Um I think a lot of these talks, a lot of these conferences, a lot of us individually uh spend a lot of time talking about building software for people who build software for people who build software, so on and so forth. And I really am just here to challenge you that there are other problems to solve than just another MCP for another SaaS solution at another company. Um but also, I'm just really trying to take advantage of a captive audience. Uh if you corner me anywhere at any time, there's a good chance I will talk to you about farming. Um so, here I am. Uh and hopefully, I can convince you to come work at Fire Crull. So, uh first things first, I believe livestock belongs on pasture. I think animals should live on grass. Um I think it's better for the animal, the consumer, the farmer, the ecosystem. I can give you a whole TED Talk on each of those if I need to. You can find me later if you need me to tell you why it's better for animals to be on the grass, but I don't have enough time to get into all of that. Take my word for it. Let's start there. The assumption is animals should be on grass. Um this is the goal I want to hit. I am not actually anti-containment farming. I think there's a reason we needed to do that, but 97% of cows are still currently uh finished on feedlots. 3% are raised on pasture. My opinion here, more animals could be on grass. I want to try to figure out how we get more animals on grass. The question is, why aren't they on grass? And that is labor is the bottleneck. It is a pain in the ass to actually raise animals on grass. Uh pasture done right actually means moving animals constantly. And that takes a lot of work. Um if you think about grass-fed uh beef, you might think of I have 100 cows, 100 acres. I put 100 cows on 100 acres. They eat grass. I got beef at the end of the year. That's not quite how it works. Um Um, will uh very rapidly decrease the quality of your pasture if you just let cows graze where they want cuz they'll graze their favorite things, ignore things that they shouldn't, trample areas consistently, so on and so forth. So, the solution to that is rotational grazing. What this means is you break up your pasture into individual paddocks where the animals have enough uh food for one one day and then you move them every single day. Um, this allows certain areas to rest and other areas to be grazed and over time will increase the efficacy of your pasture. But, this takes a whole whole whole lot of work. Um, this means you have to move fences, animals, water, and keep track of it every single day in order to uh appropriately move the animals as often as they need to. There are some solutions actually trying to work on this problem. Uh, you may have seen a company called Halter uh in the news recently. Peter Thiel invested at a $2 billion valuation. Uh, No Fence is another company. What these companies do is provide collars for the animals connected to the GPS satellites that allow you to draw virtual boundaries where you can move the animals uh remotely. Um, I think this is a great step in the direction of trying to uh expand labor. Um, but this has a problem which is you have to know where to move the animals. This is not a science to actually be honest with you. You can't just move them in a straight line across the pasture routinely every single day to the same part of land. Um, the reason is is grass doesn't grow the same every single day. Uh, there are drought conditions, rainfall, uh how much impact a particular section of the paddock has had. And the way that this is solved today is actually farmers going out on pasture, putting eyeballs on the grass, and making intuitive decisions about where the next best move should be. So, the question is how do we replace the farmers' eyes on pasture so that they can remotely make educated decisions on where to move their virtual fences. Uh there's a bit more that actually goes into this as well, and that is you can't just you have to also know how tall the grass is. Um grass has a growing cycle. If you grow it way too short, it takes really long time to come back. If you let it go too long, it becomes old and bitter and the animals don't like it. There's this juvenile sweet spot that you want to keep the grass in. You want to cut it before it gets too tall, but then you also don't want to cut it too short. So you need to keep the animals moving and then constantly coming back to the same pasture so that your grass stays at the most optimal growing age and constantly has uh the most productivity possible. So, a couple of ways that we can do this. Um these are things These are my solutions. This is something I've actually been working on thinking about how we can do this. Um a couple of options that I have are drone orthomosaic maps. If we could find a way to automate drone flights, we could go flying around our pasture, take a whole bunch of pictures, get some very high fidelity high resolution images of the grass that farmers could analyze. The problem with this is uh there's a lot of uh skill upgrade you need to do with the farmers to teach them how to fly drones, a lot of regulatory issues with keeping the drones in sight, and ideally this would be autonomous and there currently isn't a jurisdiction in the world that has approved autonomous drones for these types of applications. So this is really big bottleneck. Um I think it has pretty high fidelity in the quality of imagery, but is going to be a hard problem to solve in terms of actually getting all those hurdles accomplished. Uh satellites is my most favorite option today. There's a really cool company called Planet out there taking pictures of the entire globe every single day um with a uh 1 by 1 m resolution. Um but they're still those satellites are really high up in the sky and uh it's hard to tell some of the things you need to tell uh to actually make those educated decisions. Uh the middle photo here is actually from a friend of mine out in Missouri working as a research grad assistant at the Missouri Lincoln University. And this idea is just putting a trail cam next to a tree and some measuring apparatus that camera can look at and just figuring out how tall is the grass in relation to that particular object. Just so that we have some sort of reference point that we can use to see how well the grass is growing back. If we can solve this problem along with the the the collar situation, I think there's a world here where we can drop an LLM in the middle of this loop and start to work on autonomous grazing operations. And so what this would mean is an LLM essentially making the next best decision on where the animal should be any given day. But this isn't multivariate analysis. This requires the LLM to have several data inputs including where the animals are in GPS location, where they were yesterday, where they might go tomorrow, what the drought condition is in the area, how tall the grass is across the entire farm. And actually it has to make this decision not just on day-to-day basis, but in varying degrees of relation. So where's the best next place for a particular cow to be, but where's the best next place for the herd to be in relationship to the pasture itself, in relationship to the farm as a whole, and then more broadly the ecosystem at large. There's all of these components feed back into each other and if you can optimize this entire picture, you have a more productive farm where you can actually have more animals on fewer acres, which is how we end up actually scaling to compete with the feedlot style where you can actually have more cows on fewer grass. How do we solve this problem? There's a couple of components. There's three main blockers that I think need to exist in order for us to actually create this system. The first one is building a knowledge base and this is primarily what I'm working on at Fire Corral and then an open source project I have called Open Pasture. The idea here is a lot of the knowledge on when to move, why where how to move, the benefits of moving, etc. is all locked up in primarily YouTube videos. There's a bunch of really cool farmers out there. I can give you a whole bunch of channels you can go down rabbit holes on of just good old guys out in Missouri, Tennessee, Kentucky trying to move their animals every single day telling you what they're learning, telling you what species are best for this, what lagoons are you want to aim for in the biodiversity in your pasture. There's a whole bunch of things that go into this and we need to build that knowledge base. Fire fall is a toolkit that I used actually collect this data going out scraping those YouTube videos, scraping research papers out to archive building this knowledge base up and open pasture is the actual repository I put this information in to make it available to any farmer I think that might be able to use it. The next thing to solve is the actual visualization layer. There's a lot of components we need to know about the grass that the farmers primarily getting out of the intuition from looking at the pasture. The two main things worth figuring out about the pasture both where the animals are, where they should go and where you want them to be is what is the biomass, how much foliage actually is available for them to consume and then long-term what is the biodiversity of that particular pasture. If they overgraze sections too heavily they'll start to over index on different types of cool season, warm season grasses, lagoons, etc. and ideally you want a really rounded, really diverse pasture over time to make sure that the cattle are getting the nutrients they need so you don't have to supplement with things like hay, copper, aluminum, etc. Ideally they get all of the macronutrients and micronutrients from the grass itself which becomes an entirely ideally hands-off system. And then the third one is those geofence companies. So no fence, Halter. While I appreciate the technology they're trying to push forward I have a pretty strong disagreement with them which is in order to use their software they require you buy their collars, and you can't plug your own software into their collars. From a business standpoint, I get why this is. From an industry standpoint, I think it's really a pain in the ass. Um I would like to innovate on the software layer. I would like to push GPS locations to these collars that my LLM can predict. I don't want to have to rely on their software to do this because I don't think it's as good, or I think I can make it better, if I'm being totally honest with you. Um so, a bit of the purpose of this talk is actually a call to action for you all in the audience. I need someone to make me a collar. Um I need it to be open the APIs need to be open. Ideally, it's an off-the-shelf solution. Uh some of the component parts that we can slap together. Uh farmers are pretty scrappy and like to heal their own things. There's a lot of uh animosity towards John Deere in this sort of like right to repair. Um so, my ask to anyone maybe looking at this problem is design me a collar where the patent can be open and the APIs are open so that we can compete on software \>\> and optimize this solution. \>\> Uh the next thing I'd like to maybe tease you about is this actually goes beyond just ruminants. Uh so, ruminant is a type of animal, cows, sheep, goats. Uh those are all ruminant animals. They chew grass. They uh digest it in the rumen in uh which is an organ that's what they're called ruminants. Um but there's actually an additional benefit we get where we can stack species on these pasture rotations. This is a company called Pasture Bird. Uh they were a big catalyst for me to really get in obsessed with this idea. What they did is took their normal chicken house, put it up on big wheels, and automated the movement so it creeps its width every 24 hours across pasture. The reason you can do it this scientifically with chickens is cuz they don't actually get most of their nutrients from the grass. You have to supplement them with grain feed uh because chickens are omnivores, not quite just herbivores. Um so, you can just inch this coop across the grass uh giving them a uh uh uh land to grow on. Uh the nitrogen from their droppings actually help uh as a manure or as a as a fertilizer for for the the grass itself. And there's an added benefit here. When you stack the ruminants with the chickens, if you run your ruminants first, they sort of cut off the top of the grass, and then chickens come behind them and peck out the parasites from their droppings, and it reduces the parasite load overall across your farm, which reduces the medication expense you have to actually pay to keep your animals healthy. And over time you have a more robust uh uh seed stock or uh breeding stock so that you can have stronger animals over time that require fewer interventions and can be left alone to just eat grass and uh turn into meat eventually. Um so, the three things I really hope you all take away from this talk is one, I think we need to find big, real-world physical problems that we can solve um that require multivariate analysis and not quite uh yes or no decisions. Um there are lots of problems out there that don't actually have deterministic solutions. I hear a lot of engineers talk about how we turn LLMs into deterministic processes, and my contention is actually there's a lot of problems that you can't solve with deterministic uh algorithms. Um this is one of them. It's a multivariate analysis. There isn't a next best paddock to move to. There's just your best guess on where you think they should go. Um and I think if we can take systems like that, these uh multi-data input systems, and drop an LLM in the center to actually reason over the data and at least make a suggestion that the human can confirm or deny, uh we can really start to scale systems like this that are very much uh restricted by the farmer's ability to scale their own labor, their own decision-making power, um and really give them the tools that they need to grow their operations to hopefully, I think uh all animals could be raised on grass if we uh solve these problems. And then the last one is is maybe you can come help me solve some of these problems. Um the number one problem is actually just giving the agents the context they need, gathering the data, packaging that data, and then presenting it in a way that the LLM can reason over. And that's what we do over at Firecrawl. Uh, so you're not thinking big enough. Firecrawl is where we're building the context layer for AI, and I hope you can come build it with us. Uh, we're hiring. Uh, so here's all the job postings we currently have. Go to our website and maybe find one that works out for you. Uh, reach out to me. We'd love to have more people trying to figure out how we get data off the web to solve some of these complex problems and present that that data as context uh, to these AI agents, and perhaps we can make the world a better place. My name's Cody. Uh, Open Pastures is my open source project. Firecrawl is where I do my day-to-day life, and uh, these are my socials. I'll hang around for a little bit. I love to chat more about animals, cows, birds, uh, all the alike. Uh, thank you very much for coming. \>\> \[music\]